AC cross-check
Inline assumption checker that challenges your agent's thinking before responding. Detects complex queries and runs independent verification rounds, identifies blind spots and logical flaws. Two modes: Reinforced (same model, 2 rounds default) and Cross-Check (second model as verifier via sessions_spawn). Compact output by default, detailed on request. Use when: (1) 'cross-check this', (2) 'challenge your assumptions', (3) 'am I missing something?', (4) complex decisions, (5) long prompts where accuracy matters, (6) 'get a second opinion', (7) 'stress-test this idea'. Homepage: https://clawhub.ai/skills/cross-check
As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1091 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 622: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.